1 / 26

Effective Automatic Image Annotation Via A Coherent Language Model and Active Learning

Effective Automatic Image Annotation Via A Coherent Language Model and Active Learning. Rong Jin, Joyce Y. Chai Michigan State University Luo Si Carnegie Mellon University. ACM international conference on Multimedia 2004. Introduction. Automatic image annotation

Download Presentation

Effective Automatic Image Annotation Via A Coherent Language Model and Active Learning

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Effective Automatic Image Annotation ViaA Coherent Language Model and Active Learning Rong Jin, Joyce Y. Chai Michigan State University Luo Si Carnegie Mellon University ACM international conference onMultimedia 2004

  2. Introduction • Automatic image annotation • learn the correlation between image features and textual words from the examples of annotated images • apply the learned correlation to predicate words for unseen images • Problem • each annotated word for an image is predicated independently from other annotated words for the same image

  3. Introduction • The word-to-word correlation is important particularly when image features are insufficient in determining an appropriate word annotation • sky vs. ocean • if ‘grass’ is very likely to be an annotated word, ‘sky’ will usually be preferred over ‘ocean’

  4. Introduction • They propose a coherent language model for automatic image annotation that takes into account word-to-word correlation • It is able to automatically determine the annotation length for a given image • It can be naturally used for active learning to significantly reduce the required number of annotated image examples

  5. Related work • Machine translation model • Co-occurrence model • Latent space approaches • Graphic models • Classification approaches • Relevance language models

  6. Relevance language model • Idea • first find annotated images that are similar to a test image • use the words shared by the annotations of the similar images to annotate the test image • T: collection of annotated images • Ji={bi,1,bi,2,…,bi,m;wi,1,wi,2,…,wi,n} • Ji: annotated image • bi,j: the number of j-th blob that appears in the i-th image • wi,j: a binary variable indicating whether or not the j-th word appears in the i-th image

  7. Relevance language model • Given an image I={bi,1,bi,2,…,bi,m} • estimate the likelihood for any word to be annotated for I

  8. Coherent language model • Estimate the probability of annotating image I with a set of word {w} (p({w}|I)) • Estimate the probability for using a language model θw to generate annotation words for image I (p(θw|I)) • Θw={p1(θw), p2(θw),…, pn(θw)} • pj(θw)=p(wj=1|θw) • how likely the j-th word will be used for annotation • p(θw|I) ∝ p(I|θw) p(θw)

  9. Coherent language model

  10. Coherent language model • Use Expectation-Maximization algorithm to find the optimal solution • E-step • ZI: normalization constant that ensures • M-step • Zw: normalization constant that ensures

  11. Determining Annotation Length • It would be more appropriate to describe annotation words with Bernoulli distributions than multinomial distributions • each word is annotated at most once for an image

  12. Determining Annotation Length • is no longer a constant • a word is used for annotation if and only if the corresponding probability

  13. Active Learning for Automatic Image Annotation • Active learning • selectively sample examples for labeling so that the uncertainty in determining the right model is reduced most significantly • choosing examples that are most informative to a statistical model • For each un-annotated image, they apply the CLMFL (coherent language model with flexible length) model to determine its annotation words and compute its averaged word probability • The un-annotated image with the least averaged word probability is chosen for users to annotate.

  14. Active Learning for Automatic Image Annotation • Select the images that not only are poorly annotated by the current model but also are similar to test images • choose the images that are most similar to the test images from the set of images that the current annotation model cannot produce any annotations

  15. Experiments • Data (Duygulu, et al., 2002) • 5,000 images from 50 Corel Stock Photo CDs • Normalized cut • largest 10 regions are kept for each image • use K-means algorithm to cluster all image regions into 500 different blobs • Each image is annotated with 1 to 5 words, totally 371 distinct words • 4500 images are used as training examples and the rest 500 images are used for testing

  16. Experiments • The quality of automatic image annotation is measured by the performance of retrieving auto-annotated images regarding to single-word queries • Precision • Recall • There are totally 263 distinct words in the annotations of test images • focus on 140 words that appear at least 20 times in the training dataset

  17. Coherent Language Modelvs. Relevance Language Model • Coherent language model is better than relevance language model

  18. Coherent Language Modelvs. Relevance Language Model • Word-to-word correlation has little impact on the very top-ranked words that have been determined by the image features with high confidence • It is much more influential to the words that are not ranked at the very top • For those words, the word-to-word correlation is used to promote the words that are more consistent with the very top-ranked words

  19. Generating Annotationswith Automatically Determined Length • The average length for the generated annotations is about 3 words for each annotation • The CLMFL model performs significantly better than the CLM models when the fixed length is 3 • Two-word queries • 100 most frequent combinations of two words from the annotations of test images and use them as two-word queries

  20. Generating Annotationswith Automatically Determined Length • CLMFL model • the generated annotations are able to reflect the content of images more accurately than the CLM model that uses a fixed annotation length

  21. Generating Annotationswith Automatically Determined Length • In fifth image, ‘water’ does not appear in the annotation that is generated by the CLMFL

  22. Active Learning forAutomatic Image Annotation • First, 1000 annotated images are randomly selected from the training set and used as the initial training examples • Then, the system will iteratively acquire annotations for selected images • For each iteration, at most 20 images from the training pool can be selected for manual annotation • four iterations • at most 80 additional annotated images are acquired • At each iteration, generate annotations for the 500 testing images

  23. Active Learning forAutomatic Image Annotation • Baseline model • randomly selects 20 images for each iteration

  24. Active Learning forAutomatic Image Annotation • The active learning method provides more chance for the annotation model to learn new objects with new words

  25. Conclusion • Coherent language model • takes an advantage of word-to-word correlation • Coherent language model with flexible length • automatically determine the annotation length • Active learning method (based on the CLM model) • effectively reduce the required number of annotated images

  26. Conclusion • Future work • Learning the threshold values from training examples • have thresholds that depend the properties of annotation words • Using different measurements of uncertainty for active learning method

More Related